Wei Ke

papers

366

total citations

papers (12)

Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning

ECCV 2020arXiv

131

citations

Multiple Anchor Learning for Visual Object Detection

CVPR 2020arXiv

103

citations

Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy

CVPR 2022arXiv

citations

CoupAlign: Coupling Word-Pixel with Sentence-Mask Alignments for Referring Image Segmentation

NEURIPS 2022arXiv

citations

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

CVPR 2024arXiv

citations

Enhancing Zero-shot Object Counting via Text-guided Local Ranking and Number-evoked Global Attention

ICCV 2025

citations

Kepler codebook

ICML 2024

citations

GSHOI Denoiser: Denoising Gaussian Hand-Object Interaction Rendering

ISMAR 2025

citations

CountSE: Soft Exemplar Open-set Object Counting

ICCV 2025

citations

Wei Ke

papers (12)

Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning

Multiple Anchor Learning for Visual Object Detection

Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy

CoupAlign: Coupling Word-Pixel with Sentence-Mask Alignments for Referring Image Segmentation

Spatiotemporal Self-Supervised Learning for Point Clouds in the Wild

Generating Multimodal Driving Scenes via Next-Scene Prediction

Refining CLIP's Spatial Awareness: A Visual-Centric Perspective

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Enhancing Zero-shot Object Counting via Text-guided Local Ranking and Number-evoked Global Attention

Kepler codebook

GSHOI Denoiser: Denoising Gaussian Hand-Object Interaction Rendering

CountSE: Soft Exemplar Open-set Object Counting

papers (12)

Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning

Multiple Anchor Learning for Visual Object Detection

Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy

CoupAlign: Coupling Word-Pixel with Sentence-Mask Alignments for Referring Image Segmentation

Spatiotemporal Self-Supervised Learning for Point Clouds in the Wild

Generating Multimodal Driving Scenes via Next-Scene Prediction

Refining CLIP's Spatial Awareness: A Visual-Centric Perspective

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Enhancing Zero-shot Object Counting via Text-guided Local Ranking and Number-evoked Global Attention

Kepler codebook

GSHOI Denoiser: Denoising Gaussian Hand-Object Interaction Rendering

CountSE: Soft Exemplar Open-set Object Counting